Dynamic Contextual Generation of Creative Content for Product

This application is a continuation of U.S. patent application Ser. No. 18/823,432, filed on Sep. 3, 2024, which claims the benefit of priority to U.S. Provisional Application No. 63/538,903, filed on Sep. 18, 2023. Each of the aforementioned applications is hereby incorporated by reference in its entirety.

Various embodiments relate generally to content generation, and more particularly, to systems and methods for providing dynamic contextual generation of creative content for product listings.

The appended claims may serve as a summary of this application.

In this specification, reference is made in detail to specific embodiments of the invention. Some of the embodiments or their aspects are illustrated in the drawings.

For clarity in explanation, the invention has been described with reference to specific embodiments, however it should be understood that the invention is not limited to the described embodiments. On the contrary, the invention covers alternatives, modifications, and equivalents as may be included within its scope as defined by any patent claims. The following embodiments of the invention are set forth without any loss of generality to, and without imposing limitations on, the claimed invention. In the following description, specific details are set forth in order to provide a thorough understanding of the present invention. The present invention may be practiced without some or all of these specific details. In addition, well known features may not have been described in detail to avoid unnecessarily obscuring the invention.

In addition, it should be understood that steps of the exemplary methods set forth in this exemplary patent can be performed in different orders than the order presented in this specification. Furthermore, some steps of the exemplary methods may be performed in parallel rather than being performed sequentially. Also, the steps of the exemplary methods may be performed in a network environment in which some steps are performed by different computers in the networked environment.

Some embodiments are implemented by a computer system. A computer system may include a processor, a memory, and a non-transitory computer-readable medium. The memory and non-transitory medium may store instructions for performing methods and steps described herein.

In the field of online content generation and user engagement optimization, the rapid evolution of e-commerce and digital advertising platforms has ushered in a new era of personalized content delivery. The significance of optimizing user engagement, particularly in the context of product listings, cannot be overstated. Effective user engagement can be a decisive factor in achieving sales, brand recognition, and overall success within digital platforms. However, prior methods of addressing this challenge have been encumbered by limitations that have hindered their ability to meet the dynamic and highly competitive nature of modern digital environments.

Historically, traditional product listings on e-commerce platforms have been static in nature, often consisting of fixed images, text descriptions, and basic product details. These static listings, while informative, lacked the adaptability required to cater to the diverse and evolving needs of online shoppers. Furthermore, the challenge of creating compelling and personalized content for each user proved to be a formidable task, often resulting in a one-size-fits-all approach. These limitations not only hampered the user experience but also hindered the ability of sellers and advertisers to maximize the potential of their products within the online marketplace.

Efforts to address these limitations led to the development of early content optimization techniques, which often relied on rule-based systems or rudimentary recommendation engines. These systems attempted to personalize content by considering user history and preferences, yet they frequently fell short in delivering truly dynamic and engaging experiences. Moreover, these approaches lacked the capability to adapt to rapidly changing market conditions, user behavior, and emerging trends. This rendered them inadequate for meeting the demands of modern digital platforms where competition is fierce, and user expectations are constantly evolving.

As the digital landscape evolved, the limitations of rule-based and recommendation systems became more apparent. The need for a more sophisticated and adaptable approach to content generation and user engagement optimization became evident. This led to the emergence of artificial intelligence (“AI”) and machine learning (“ML”) as potential solutions. These technologies held promise in their ability to harness vast datasets and adapt in real-time to user behavior and preferences. However, early AI and ML models faced their own set of challenges, including the need for substantial training data, computational resources, and a mechanism to continually refine and optimize content.

Thus, the current techniques for user engagement optimization for digital content, particularly product listings, have been marked by static and rule-based approaches that struggled to deliver dynamic, personalized, and adaptable experiences for users. As the digital landscape evolved, these limitations became increasingly apparent, driving the need for more sophisticated solutions. The emergence of AI and ML have presented promising avenues for improvement, but significant challenges remain in terms of data, computational requirements, and ongoing optimization.

Thus, there is a need in the field of content generation to create a new and useful system and method for providing dynamic contextual generation of creative content for product listings. The source of the problem, as discovered by the inventors, is the absence of a system capable of harnessing AI and ML techniques to create highly personalized, dynamic, and contextually relevant content for product listings in real-time. This system should not only meet user engagement objectives, but also empower sellers and advertisers to maximize the potential of their products within digital platforms.

In one embodiment, the system receives one or more initial product facts for a product, wherein the product has been requested to be listed within a platform, user engagement data for a user of the platform, and one or more pieces of contextual information related to how the product will be viewed within the platform; uses the initial product facts, the user engagement data, and the pieces of contextual information to train a generative AI model for dynamic creative content generation for the listing; uses the trained generative AI model to dynamically generate one or more pieces of creative content for the listing; displays the one or more pieces of creative content for the listing on a client device associated with the user; receives feedback regarding user engagement with the pieces of creative content in terms of whether an engagement objective has been achieved; and refines the generative AI model based on the received feedback, including optimizing the generative AI model to generate or modify the pieces of creative content to achieve the engagement objective.

Further areas of applicability of the present disclosure will become apparent from the remainder of the detailed description, the claims, and the drawings. The detailed description and specific examples are intended for illustration only and are not intended to limit the scope of the disclosure.

is a diagram illustrating an exemplary environment in which some embodiments may operate. In the exemplary environment, a client device, and a platformare connected to a processing engine. The processing engineis optionally connected to one or more repositories and/or databases. Such repositories and/or databases may include, for example, a product facts repository, a user engagement repository, and a creative content repository. One or more of such repositories may be combined or split into multiple repositories. The client devicein this environment may be a computer, and the platformand processing enginemay be, in whole or in part, applications or software hosted on a computer or multiple computers which are communicatively coupled via remote server or locally.

The exemplary environmentis illustrated with only one client device, one processing engine, and one platform, though in practice there may be more or fewer additional client devices, processing engines, and/or platforms. In some embodiments, the client device, processing engine, and/or platform may be part of the same computer or device.

In an embodiment, the processing enginemay perform the method() or other method herein and, as a result, provide for dynamic contextual generation of creative content for product listings. In some embodiments, this may be accomplished via communication with the client device, additional client device(s), processing engine, platform, and/or other device(s) over a network between the device(s) and an application server or some other network server. In some embodiments, one or both of the processing engineand platformmay be an application, browser extension, or other piece of software hosted on a computer or similar device, or in itself a computer or similar device configured to host an application, browser extension, or other piece of software to perform some of the methods and embodiments herein.

In some embodiments, the processing engineperforms processing tasks partially or entirely on the client devicein a manner that is local to the device and relies on the device's local processor and capabilities. In some embodiments, the processing enginemay perform processing tasks in a manner such that some specific processing tasks are performed locally, such as, e.g., visual AI processing tasks, while other processing tasks are performed remotely via one or more connected servers. In yet other embodiments, the processing enginemay processing tasks entirely remotely.

In some embodiments, client devicemay be a device with a display configured to present information to a user of the device. In some embodiments, the client devicepresents information in the form of a user interface (UI) with UI elements or components. In some embodiments, the client devicesends and receives signals and/or information to the processing enginepertaining to the communication platform. In some embodiments, client deviceis a computer device capable of hosting and executing one or more applications or other programs capable of sending and/or receiving information. In some embodiments, the client devicemay be a computer desktop or laptop, mobile phone, virtual assistant, virtual reality or augmented reality device, wearable, or any other suitable device capable of sending and receiving information. In some embodiments, the processing engineand/or platformmay be hosted in whole or in part as an application or web service executed on the client device. In some embodiments, one or more of the communication platform, processing engine, and client devicemay be the same device. In some embodiments, the platformand/or the client deviceare associated with one or more particular user accounts.

In some embodiments, optional repositories function to store and/or maintain, respectively, product facts related to a product, user engagement data, and creative content generated for product listings. The optional repositories may also store and/or maintain any other suitable information for the processing engineto perform elements of the methods and systems herein pertaining to the platform. In some embodiments, the optional database(s) can be queried by one or more components of system(e.g., by the processing engine), and specific stored data in the database(s) can be retrieved.

The platform is a platform configured to provide dynamic, contextual generation of creative content. In some embodiments, the platform may be hosted within an application that can be executed on the user's client device, such as a smartphone application.

is a diagram illustrating an exemplary computer systemwith software modules that may execute some of the functionality described herein. In some embodiments, the modules illustrated are components of the processing engine.

Receiving modulefunctions to receive one or more initial product facts for a product, wherein the product has been requested to be listed within a platform; user engagement data for a user of the platform; and one or more pieces of contextual information related to how the product will be viewed within the platform.

Training modulefunctions to uses the initial product facts, the user engagement data, and the pieces of contextual information to train a generative AI model for dynamic creative content generation for the listing.

Generation modulefunctions to uses the trained generative AI model to dynamically generate one or more pieces of creative content for the listing.

Displaying modulefunctions to display the one or more pieces of creative content for the listing on a client device associated with the user.

Feedback modulefunctions to receive feedback regarding user engagement with the pieces of creative content in terms of whether an engagement objective has been achieved.

Refinement modulefunctions to refine the generative AI model based on the received feedback, including optimizing the generative AI model to generate or modify the pieces of creative content to achieve the engagement objective.

The functionality of the above modules will be described in further detail with respect to the exemplary method ofbelow.

is a flow chart illustrating an exemplary method that may be performed in some embodiments.

At step, the system receives one or more initial product facts for a product, wherein the product has been requested to be listed within a platform, user engagement data for a user of the platform, and one or more pieces of contextual information related to how the product will be viewed within the platform.

In some embodiments, the system receives one or more initial product facts for a product, which refers to various pieces of information about a product which may be relevant or necessary for creating accurate and informative product listings or descriptions within a digital platform. These product facts may provide a comprehensive understanding of the product and its key attributes, characteristics, and/or details. In various embodiments, such product facts may include, for example: a product title, a product description, one or more product images, a price or fee, product availability, technical specifications and/or features of the product, reviews and/or ratings of the product, variations of the product, options for purchasing the product, warranty information, return policy, product brand, product manufacturer, product distributor, or any other relevant product information.

In some embodiments, the system receives user engagement data for a user of the platform, which provides the system with data on, e.g., user's behavior, preferences, and/or interactions within the digital platform. It can include, for example, information on completed sales associated with the user, user interactions with various elements of the platform, and/or the user's viewing patterns.

In some embodiments, the user engagement data includes signals or pieces of information regarding one or more of: data on completed sales associated with the user on a platform where the listing is hosted, data on user interaction with one or more interactive elements of the listing, and data on user viewing of elements of the listing. First, the user engagement data may include data on completed sales associated with the user on the platform where the listing is hosted. This data can include records of, e.g., the user's past purchases, providing valuable information about their preferences and buying history. By analyzing these sales records, the generative artificial intelligence (AI) model can tailor the creative content to align with the user's previous purchasing behavior, increasing the likelihood of future sales. Second, the user engagement data can encompass data on user interaction with one or more interactive elements of the product listing. This can involve tracking how users engage with various components of the listing, such as, e.g., clicking on product images, reading descriptions, or interacting with buttons like “add to cart.” In some embodiments, the AI model can use this information to optimize the placement and design of interactive elements in the creative content. Additionally, the user engagement data may include data on user viewing of elements within the product listing. This data can provide insights into what aspects of the listing capture the user's attention and for how long. By analyzing user viewing patterns, the AI model can emphasize or modify certain elements in the creative content to maximize user engagement.

In some embodiments, the system receives one or more pieces of contextual information related to how the product will be viewed within the platform, which adds a layer of adaptability and responsiveness to the content generation process. Context is a critical factor when determining how to generate creative content for a product listing. In various embodiments, this contextual information can include, for example, details such as the time of day, the geographic location of the user, and/or the specific search query employed by the user. Incorporating this contextual information ensures that the generated content is not only user-specific, but also contextually relevant, increasing the likelihood of capturing the user's interest.

At step, the system uses the initial product facts, the user engagement data, and the pieces of contextual information to train a generative AI model for dynamic creative content generation for the listing. In some embodiments, this process leverages machine learning and AI techniques to train the generative AI model to create tailored and contextually relevant creative content for product listings within a digital platform.

In some embodiments, the initial product facts serve as inputs for the model's training to include details such as, e.g., the product's title, description, and images. In some embodiments, the user engagement data is additionally used as input for the model's training to take into account the behavior and preferences of the platform's users when generating creative content for a product listing. In some embodiments, the inclusion of contextual information adds an additional layer of input to the AI model's training. Contextual information pertains to how the product will be perceived or viewed within the platform, considering factors like the time of day, geographic location of the user, and the user's search query. This contextual insight allows the AI model to adapt creative content generation to align with specific user scenarios, making it more relevant and appealing.

In some embodiments, the AI model's training involves using machine learning algorithms to identify patterns, relationships, and trends within the combined dataset of product facts, user engagement data, and contextual information. It learns to recognize which product attributes and content elements are most effective in engaging users and driving desired outcomes, such as sales or interactions. As a result of this training, the AI model becomes proficient in dynamically generating creative content for product listings. This content can include product titles, descriptions, and images tailored to suit different user contexts and preferences. The dynamic nature of content generation ensures that product listings remain fresh and relevant, adapting to evolving user behavior and market dynamics.

In some embodiments, the generative AI model is a large language model (hereinafter “LLM”). An LLM is a type of artificial intelligence model that is specifically designed to process and generate human language. These models are characterized by their extensive training on vast corpora of text data, allowing them to understand and generate text in a coherent and contextually relevant manner. In various embodiments, LLMs can be leveraged in various ways to enhance the effectiveness of the creative content being generated.

In various embodiments, LLMs can be used for one or more of: creating compelling product titles, descriptions, and/or promotional messages; adapting the tone of the content based on user engagement data and contextual information; ensuring that the generated text resonates with the target audience; analyzing and understanding natural language queries, reviews, comments, conversations, and feedback from users related to products; generating content in multiple languages based on geographical location; analyzing user engagement data to understand individual preferences; employing sentiment analysis to gauge user sentiment towards products and tailor content accordingly; identifying relevant keywords and phrases that are currently trending or commonly used in the platform; generating diverse content variations for the same product; creating multiple versions of creative content for A/B testing; and any other relevant purpose an LLM may be used for.

In some embodiments, the generative AI model uses a deep learning architecture. Deep learning represents a subset of machine learning that mimics the human brain's neural networks to process and analyze vast amounts of data. In some embodiments, the generative AI model's deep learning architecture enables it to continuously learn and improve its creative content generation abilities over time. Deep learning models can efficiently process and analyze large datasets, including extensive data on, e.g., product listings, user behavior, and/or platform dynamics.

In some embodiments, the generative AI model is additionally trained on user engagement and sales data to optimize for maximized sales. To achieve this, the system leverages the wealth of data available regarding user behavior and sales patterns. Training the model on sales data provides insights into what product listings and creative content have historically led to successful transactions. This information can be useful in training the generative AI model to generate content that aligns with user preferences and market trends.

In some embodiments, the generative AI model is additionally trained on one or more previous listings which are not currently listed within the environment. This can be useful when previous listings can provide insights into market trends and/or changing user preferences over time, when products have seasonal or cyclical popularity or context, when products are relisted after being previously listed on the platform, or any other relevant purpose.

In some embodiments, the generative AI model is trained further on a large dataset of listings. The broader and more diverse the dataset the model is trained on, the more adept it becomes at understanding user behavior, platform intricacies, and market trends. By training the generative AI model on a substantial dataset of listings, the system ensures that the creative content being produced is not only contextually relevant but also adaptable to various users, platforms, and contexts. In some embodiments, this additional training on a large dataset of listings empowers the AI model with a wealth of knowledge about, e.g., various products, markets, and consumer preferences.

At step, the system uses the trained generative AI model to dynamically generate one or more pieces of creative content for the listing. Upon the completion of the training in step, the generative AI model is now trained to generative creative content based on the insights and understanding of how to do so that was gained from the initial product facts, user engagement data, and contextual information as training inputs. In some embodiments, the piece of creative content is generated based on features that are both true and relevant to the specifics of the user engagement data, the contextual listing data, and the initial product facts. The generative AI model then leverages this comprehensive understanding to generate creative content that is not only relevant, but also optimized for user engagement.

The term “creative content” encompasses various elements that contribute to an appealing product listing. These elements can include, e.g., product titles, descriptions, and images. In some embodiments, the generative AI model's dynamic generation capabilities mean that it can adapt these elements based on the specific circumstances of the user and the product to generate different pieces of creative content for the same product listing, depending on, e.g., different contexts or users with differing preferences or engagement behaviors. For example, the generative AI model may generate different product titles for morning and evening shoppers, or tailor product descriptions differently to resonate with two different users located in different geographic regions.

In some embodiments, the generative AI model's ability to generate multiple pieces of creative content is advantageous. It provides flexibility for testing different approaches and variations to determine what resonates most effectively with users. In some embodiments, this process of content generation and testing is iterative, contributing to the continuous refinement of product listings, improving their overall performance.

In some embodiments, the piece of creative content is generated by the generative AI model to differ from one or more additional product listings presented concurrently to the user. In some embodiments, the generated piece of creative content is generated at least in part with an objective to compete with other concurrent listings within the environment to prevent all concurrent listings from having too-similar creative content. In some embodiments, the generated piece of creative content is generated at least in part to satisfy an objective of diversity in creative content with respect to concurrent listings within the environment according to user perception.

By producing creative content that highlights unique niches or features of a product that other products lack, the system can capture users' attention and encourage them to explore further. To achieve this differentiation, the system's generative AI model strategically analyzes the competition. It assesses the creative content of other listings, considering factors like product descriptions, titles, and images. The system then leverages this information to generate creative content that sets the product apart from the competition. For example, if several listings offer similar smartphones, the system may choose to highlight unique features of a particular phone, such as its advanced camera technology or exceptional battery life. By doing so, the generated content ensures that each listing offers something distinct, preventing redundancy and aiding users in making informed decisions.